Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Predator-Prey Interactions02:39

Predator-Prey Interactions

16.2K
Predators consume prey for energy. Predators that acquire prey and prey that avoid predation both increase their chances of survival and reproduction (i.e., fitness). Routine predator-prey interactions elicit mutual adaptations that improve predator offenses, such as claws, teeth, and speed, as well as prey defenses, including crypsis, aposematism, and mimicry. Thus, predator-prey interactions resemble an evolutionary arms race.
16.2K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Fine-grained 3D rice phenotyping via multi-scale NeRF and multimodal segmentation.

Plant phenomics (Washington, D.C.)·2026
Same author

Schwann cell derived extracellular vesicles are multifunctional nanotherapeutic mediators for diabetic oral mucosal wound healing.

Discover nano·2026
Same author

IPENS: Interactive unsupervised framework for rapid plant phenotyping extraction via NeRF-SAM2 fusion.

Plant phenomics (Washington, D.C.)·2026
Same author

<i>De novo</i> binders overcome the MMLV RT stability-activity trade-off.

iScience·2025
Same author

Extracellular vesicles from hypoxia preconditioned bone marrow mesenchymal stem cell improve peri-implant osteogenesis under type 2 diabetes condition.

Journal of controlled release : official journal of the Controlled Release Society·2025
Same author

Thread design optimization of a dental implant using explicit dynamics finite element analysis.

Scientific reports·2025

相关实验视频

Updated: Jun 22, 2025

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches
07:23

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches

Published on: August 4, 2014

23.0K

用记忆进行相互学习,用于半监督的害虫检测.

Jiale Zhou1,2, He Huang2,3, Youqiang Sun2

  • 1Science Island Branch, Graduate School of USTC, Hefei, China.

Frontiers in plant science
|July 2, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了PestTeacher,这是一种半监督的计算机视觉方法,用于精准农业中准确检测害虫. 它使用仅20%的标记数据实现了80%的有效性,大大改善了害虫识别和管理.

关键词:
具有空间意识的多分辨率特征提取布式 RPN RPN 的时间.记忆 记忆 融合 融合相互学习的相互学习.半监督的虫害检测 半监督的虫害检测

更多相关视频

Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.2K
Visual Classical Conditioning in Wood Ants
05:46

Visual Classical Conditioning in Wood Ants

Published on: October 5, 2018

8.3K

相关实验视频

Last Updated: Jun 22, 2025

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches
07:23

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches

Published on: August 4, 2014

23.0K
Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.2K
Visual Classical Conditioning in Wood Ants
05:46

Visual Classical Conditioning in Wood Ants

Published on: October 5, 2018

8.3K

科学领域:

  • 农业科学 农业科学
  • 计算机视觉 计算机视觉
  • 机器学习 机器学习

背景情况:

  • 精准农业需要有效的害虫监测,以防止作物损失.
  • 计算机视觉在害虫检测方面面临挑战,原因是尺度变化,复杂的背景和密集的分布.
  • 对象检测的监督学习需要大量的标记数据,这往往是不切实际的.

研究的目的:

  • 为了开发一个创新的半监督的害虫检测框架,PestTeacher.
  • 为了克服确认偏差和代检测结果的不稳定性.
  • 在具有挑战性的农业场景中提高害虫检测的准确性.

主要方法:

  • 实施了PestTeacher,这是一个新的半监督物体检测框架.
  • 引入了空间意识多分辨率特征提取 (SMFE) 模块,以解决弱害虫特征.
  • 使用级联区域提案网络 (RPN) 模块生成高质量的物体检测.

主要成果:

  • 在只有20%的监督训练数据的情况下,PestTeacher在玉米和Pest24数据集上实现了大约80%的有效性.
  • 该模型显示,与基线SoftTeacher的4.6.4相比,平均平均精度 (mAP@0.5) 的7.3显著改善.
  • 拟议的方法有效地减轻了确认偏差和检测不稳定性等问题.

结论:

  • PestTeacher提供了一种高效的半监督方法,用于在农业中自动识别害虫.
  • 该框架为开发先进的害虫管理解决方案提供了有价值的技术参考.
  • 这项研究有助于通过早期和准确的害虫检测来最大限度地减少产量损失.